混合复数网络提升雷达图像分类准确率
PolSAR Image Classification using a Hybrid Complex-Valued Network (HybridCVNet)
- 融合复数卷积与视觉变换器，利用相位信息增强特征提取
- 在弗莱沃兰数据集上达97.39%准确率，1%采样时卡帕值0.972
- 适合处理含相位信息的极化合成孔径雷达图像任务
近年来，卷积神经网络（CNN）因其在计算机视觉任务中的有效性而广受欢迎。研究人员正探索视觉变换器（ViT）在遥感与地球观测中的潜力。然而，传统实值网络常忽略极化合成孔径雷达（PolSAR）等复数数据中的重要相位信息。为此，新型复数深度架构应运而生。HybridCVNet是一种新型混合网络，结合了复数卷积神经网络（CV-CNN）与复数视觉变换器（CV-ViT）技术。它通过高效集成三维与二维复数卷积网络作为特征提取器，增强了对PolSAR图像中互补信息的提取，并有效利用数据内部的依赖关系。在多个广泛使用的PolSAR数据集上的实验结果表明，HybridCVNet优于其他方法，在弗莱沃兰数据集上达到97.39%的整体准确率；即使仅使用1%的样本比例，也在旧金山数据集上取得0.972的卡帕值。源代码可通过https://github.com/mqalkhatib/HybridCVNet获取。
原文摘要 · Abstract (English)
Recently, convolutional neural networks (CNNs) have become popular for image classification due to their effectiveness in computer vision tasks. Now, researchers are exploring the potential of vision transformers (ViTs) in remote sensing and Earth observation. However, traditional Real-Valued networks often overlook important phase information in Complex-Valued (CV) data like polarimetric synthetic aperture radar (PolSAR) data. To address this, new CV deep architectures have emerged. HybridCVNet, a novel hybrid network, blends CV-CNN and CV vision transformer (CV-ViT) techniques. It efficiently combines CV 3D and 2D CNNs as feature extractors, enhancing PolSAR image classification by extracting complementary information and effectively leveraging interdependencies within the data. Experimental results from widely-used PolSAR datasets show HybridCVNet outperforms other methods, achieving an overall accuracy of 97.39% on the Flevoland dataset and showing promise even with just a 1% sampling ratio, with a Kappa value of 0.972 on the San Francisco dataset. Source code is accessible through https://github.com/mqalkhatib/HybridCVNet
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。